Exploring complementary information of self-supervised pretext tasks for unsupervised video pre-training.
Wei ZhouYi HouKewei OuyangShilin ZhouPublished in: IET Comput. Vis. (2022)
Keyphrases
- video sequences
- information sources
- prior knowledge
- structural information
- space time
- domain knowledge
- information processing
- multimedia information
- real time
- visual cues
- visual data
- multimedia data
- information sharing
- spatial information
- user interaction
- visual features
- text classification
- information extraction
- end users
- feature space